针对现有人体姿态迁移方法因编码阶段特征处理不当导致图像变形失真的问题,提出基于Pose-Attentional Transfer Network(PATN)和自注意力机制的多分辨率人体姿态迁移方法。首先,设计了姿态引导自注意力模块,通过多头注意力机制增强关键...针对现有人体姿态迁移方法因编码阶段特征处理不当导致图像变形失真的问题,提出基于Pose-Attentional Transfer Network(PATN)和自注意力机制的多分辨率人体姿态迁移方法。首先,设计了姿态引导自注意力模块,通过多头注意力机制增强关键身体区域特征通道的权重,并减小背景无关特征的影响,自适应地探索两条支路特征之间的关联性;其次,在解码阶段加入多尺度注意力模块,增强不同尺度的姿态信息表达,有效提升局部细节和整体纹理的保真度;最后,引入三元像素损失对生成图像进行约束,提高了图像的特征一致性和结构一致性。在DeepFashion和Market-1501数据集上进行验证,实验结果表明,本文方法在结构相似性(SSIM)、初始评分(IS)、感知相似度(LPIPS)指标上均优于现有的PATN方法,并且在视觉感观、边缘纹理方面均有所提升,在行人重识别的下游任务中具有重要的潜力。展开更多
The growing spectrum of Generative Adversarial Network (GAN) applications in medical imaging, cyber security, data augmentation, and the field of remote sensing tasks necessitate a sharp spike in the criticality of re...The growing spectrum of Generative Adversarial Network (GAN) applications in medical imaging, cyber security, data augmentation, and the field of remote sensing tasks necessitate a sharp spike in the criticality of review of Generative Adversarial Networks. Earlier reviews that targeted reviewing certain architecture of the GAN or emphasizing a specific application-oriented area have done so in a narrow spirit and lacked the systematic comparative analysis of the models’ performance metrics. Numerous reviews do not apply standardized frameworks, showing gaps in the efficiency evaluation of GANs, training stability, and suitability for specific tasks. In this work, a systemic review of GAN models using the PRISMA framework is developed in detail to fill the gap by structurally evaluating GAN architectures. A wide variety of GAN models have been discussed in this review, starting from the basic Conditional GAN, Wasserstein GAN, and Deep Convolutional GAN, and have gone down to many specialized models, such as EVAGAN, FCGAN, and SIF-GAN, for different applications across various domains like fault diagnosis, network security, medical imaging, and image segmentation. The PRISMA methodology systematically filters relevant studies by inclusion and exclusion criteria to ensure transparency and replicability in the review process. Hence, all models are assessed relative to specific performance metrics such as accuracy, stability, and computational efficiency. There are multiple benefits to using the PRISMA approach in this setup. Not only does this help in finding optimal models suitable for various applications, but it also provides an explicit framework for comparing GAN performance. In addition to this, diverse types of GAN are included to ensure a comprehensive view of the state-of-the-art techniques. This work is essential not only in terms of its result but also because it guides the direction of future research by pinpointing which types of applications require some GAN architectures, works to improve specific task model selection, and points out areas for further research on the development and application of GANs.展开更多
At present,noise reduction has become an urgent challenge across various fields.Whether in the context of household appliances in daily life or in the enhancement of stealth performance in military equipment,noise con...At present,noise reduction has become an urgent challenge across various fields.Whether in the context of household appliances in daily life or in the enhancement of stealth performance in military equipment,noise control technologies play a critical role.This study introduces a computational framework for simulating Helmholtz equationgoverned acoustic scattering using a boundary element method(BEM)integrated with Loop subdivision surfaces.By adopting the Loop subdivision scheme—a widely used computer-aided design(CAD)technique-the framework unifies geometric representation and physical field discretization,ensuring seamless compatibility with industrial CAD workflows.The core innovation lies in the novel integration of conditional generative adversarial networks(CGANs)into the subdivision surface BEM to assist and accelerate the numerical computation process.In this study,for the two cases examined,the results show that the CGAN-enhanced approach achieves substantial gains in computational efficiency without compromising accuracy.A hierarchical acceleration strategy is further proposed:the fast multipole method(FMM)first reduces baseline computational complexity,while CGAN-driven secondary acceleration and data augmentation enable real-time parameter exploration.Benchmark validations and practical engineering applications demonstrate the method’s robustness and scalability for large-scale structural-acoustic analysis.展开更多
Under complex flight conditions,such as obstacle avoidance and extreme sea state,wing-in-ground(WIG)effect aircraft need to ascend to higher altitudes,resulting in the disappearance of the ground effect.A design of hi...Under complex flight conditions,such as obstacle avoidance and extreme sea state,wing-in-ground(WIG)effect aircraft need to ascend to higher altitudes,resulting in the disappearance of the ground effect.A design of high-speed WIG airfoil considering non-ground effect is carried out by a novel two-step inverse airfoil design method that combines conditional generative adversarial network(CGAN)and artificial neural network(ANN).The CGAN model is employed to generate a variety of airfoil designs that satisfy the desired lift-drag ratios in both ground effect and non-ground effect conditions.Subsequently,the ANN model is utilized to forecast aerodynamic parameters of the generated airfoils.The results indicate that the CGAN model contributes to a high accuracy rate for airfoil design and enables the creation of novel airfoil designs.Furthermore,it demonstrates high accuracy in predicting aerodynamic parameters of these airfoils due to the ANN model.This method eliminates the necessity for numerical simulations and experimental testing through the design procedure,showcasing notable efficiency.The analysis of airfoils generated by the CGAN model shows that airfoils exhibiting high lift-drag ratios under both flight conditions typically have cambers of among[0.08c,0.105c],with the positions of maximum camber occurring among[0.35c,0.5c]of the chord length,and the leading-edge radiuses of these airfoils primarily cluster among[0.008c,0.025c]展开更多
Pneumonia ranks as a leading cause of mortality, particularly in children aged five and under. Detecting this disease typically requires radiologists to examine chest X-rays and report their findings to physicians, a ...Pneumonia ranks as a leading cause of mortality, particularly in children aged five and under. Detecting this disease typically requires radiologists to examine chest X-rays and report their findings to physicians, a task susceptible to human error. The application of Deep Transfer Learning (DTL) for the identification of pneumonia through chest X-rays is hindered by a shortage of available images, which has led to less than optimal DTL performance and issues with overfitting. Overfitting is characterized by a model’s learning that is too closely fitted to the training data, reducing its effectiveness on unseen data. The problem of overfitting is especially prevalent in medical image processing due to the high costs and extensive time required for image annotation, as well as the challenge of collecting substantial datasets that also respect patient privacy concerning infectious diseases such as pneumonia. To mitigate these challenges, this paper introduces the use of conditional generative adversarial networks (CGAN) to enrich the pneumonia dataset with 2690 synthesized X-ray images of the minority class, aiming to even out the dataset distribution for improved diagnostic performance. Subsequently, we applied four modified lightweight deep transfer learning models such as Xception, MobileNetV2, MobileNet, and EfficientNetB0. These models have been fine-tuned and evaluated, demonstrating remarkable detection accuracies of 99.26%, 98.23%, 97.06%, and 94.55%, respectively, across fifty epochs. The experimental results validate that the models we have proposed achieve high detection accuracy rates, with the best model reaching up to 99.26% effectiveness, outperforming other models in the diagnosis of pneumonia from X-ray images.展开更多
文摘针对现有人体姿态迁移方法因编码阶段特征处理不当导致图像变形失真的问题,提出基于Pose-Attentional Transfer Network(PATN)和自注意力机制的多分辨率人体姿态迁移方法。首先,设计了姿态引导自注意力模块,通过多头注意力机制增强关键身体区域特征通道的权重,并减小背景无关特征的影响,自适应地探索两条支路特征之间的关联性;其次,在解码阶段加入多尺度注意力模块,增强不同尺度的姿态信息表达,有效提升局部细节和整体纹理的保真度;最后,引入三元像素损失对生成图像进行约束,提高了图像的特征一致性和结构一致性。在DeepFashion和Market-1501数据集上进行验证,实验结果表明,本文方法在结构相似性(SSIM)、初始评分(IS)、感知相似度(LPIPS)指标上均优于现有的PATN方法,并且在视觉感观、边缘纹理方面均有所提升,在行人重识别的下游任务中具有重要的潜力。
文摘The growing spectrum of Generative Adversarial Network (GAN) applications in medical imaging, cyber security, data augmentation, and the field of remote sensing tasks necessitate a sharp spike in the criticality of review of Generative Adversarial Networks. Earlier reviews that targeted reviewing certain architecture of the GAN or emphasizing a specific application-oriented area have done so in a narrow spirit and lacked the systematic comparative analysis of the models’ performance metrics. Numerous reviews do not apply standardized frameworks, showing gaps in the efficiency evaluation of GANs, training stability, and suitability for specific tasks. In this work, a systemic review of GAN models using the PRISMA framework is developed in detail to fill the gap by structurally evaluating GAN architectures. A wide variety of GAN models have been discussed in this review, starting from the basic Conditional GAN, Wasserstein GAN, and Deep Convolutional GAN, and have gone down to many specialized models, such as EVAGAN, FCGAN, and SIF-GAN, for different applications across various domains like fault diagnosis, network security, medical imaging, and image segmentation. The PRISMA methodology systematically filters relevant studies by inclusion and exclusion criteria to ensure transparency and replicability in the review process. Hence, all models are assessed relative to specific performance metrics such as accuracy, stability, and computational efficiency. There are multiple benefits to using the PRISMA approach in this setup. Not only does this help in finding optimal models suitable for various applications, but it also provides an explicit framework for comparing GAN performance. In addition to this, diverse types of GAN are included to ensure a comprehensive view of the state-of-the-art techniques. This work is essential not only in terms of its result but also because it guides the direction of future research by pinpointing which types of applications require some GAN architectures, works to improve specific task model selection, and points out areas for further research on the development and application of GANs.
基金the support from the 2025 Henan Provincial Science and Technology Research Project,the Zhumadian 2023 Major Science and Technology Special Projectthe Postgraduate Education Reform and Quality Improvement Project of Henan Province.
文摘At present,noise reduction has become an urgent challenge across various fields.Whether in the context of household appliances in daily life or in the enhancement of stealth performance in military equipment,noise control technologies play a critical role.This study introduces a computational framework for simulating Helmholtz equationgoverned acoustic scattering using a boundary element method(BEM)integrated with Loop subdivision surfaces.By adopting the Loop subdivision scheme—a widely used computer-aided design(CAD)technique-the framework unifies geometric representation and physical field discretization,ensuring seamless compatibility with industrial CAD workflows.The core innovation lies in the novel integration of conditional generative adversarial networks(CGANs)into the subdivision surface BEM to assist and accelerate the numerical computation process.In this study,for the two cases examined,the results show that the CGAN-enhanced approach achieves substantial gains in computational efficiency without compromising accuracy.A hierarchical acceleration strategy is further proposed:the fast multipole method(FMM)first reduces baseline computational complexity,while CGAN-driven secondary acceleration and data augmentation enable real-time parameter exploration.Benchmark validations and practical engineering applications demonstrate the method’s robustness and scalability for large-scale structural-acoustic analysis.
基金supported by the Priority Academic Program Development of Jiangsu Higher Education Institutions,the Fundamental Research Funds for the Central Universities(No.ILA220101A23)CARDC Fundamental and Frontier Technology Research Fund(No.PJD20200210)the Aeronautical Science Foundation of China(No.20200023052002).
文摘Under complex flight conditions,such as obstacle avoidance and extreme sea state,wing-in-ground(WIG)effect aircraft need to ascend to higher altitudes,resulting in the disappearance of the ground effect.A design of high-speed WIG airfoil considering non-ground effect is carried out by a novel two-step inverse airfoil design method that combines conditional generative adversarial network(CGAN)and artificial neural network(ANN).The CGAN model is employed to generate a variety of airfoil designs that satisfy the desired lift-drag ratios in both ground effect and non-ground effect conditions.Subsequently,the ANN model is utilized to forecast aerodynamic parameters of the generated airfoils.The results indicate that the CGAN model contributes to a high accuracy rate for airfoil design and enables the creation of novel airfoil designs.Furthermore,it demonstrates high accuracy in predicting aerodynamic parameters of these airfoils due to the ANN model.This method eliminates the necessity for numerical simulations and experimental testing through the design procedure,showcasing notable efficiency.The analysis of airfoils generated by the CGAN model shows that airfoils exhibiting high lift-drag ratios under both flight conditions typically have cambers of among[0.08c,0.105c],with the positions of maximum camber occurring among[0.35c,0.5c]of the chord length,and the leading-edge radiuses of these airfoils primarily cluster among[0.008c,0.025c]
文摘Pneumonia ranks as a leading cause of mortality, particularly in children aged five and under. Detecting this disease typically requires radiologists to examine chest X-rays and report their findings to physicians, a task susceptible to human error. The application of Deep Transfer Learning (DTL) for the identification of pneumonia through chest X-rays is hindered by a shortage of available images, which has led to less than optimal DTL performance and issues with overfitting. Overfitting is characterized by a model’s learning that is too closely fitted to the training data, reducing its effectiveness on unseen data. The problem of overfitting is especially prevalent in medical image processing due to the high costs and extensive time required for image annotation, as well as the challenge of collecting substantial datasets that also respect patient privacy concerning infectious diseases such as pneumonia. To mitigate these challenges, this paper introduces the use of conditional generative adversarial networks (CGAN) to enrich the pneumonia dataset with 2690 synthesized X-ray images of the minority class, aiming to even out the dataset distribution for improved diagnostic performance. Subsequently, we applied four modified lightweight deep transfer learning models such as Xception, MobileNetV2, MobileNet, and EfficientNetB0. These models have been fine-tuned and evaluated, demonstrating remarkable detection accuracies of 99.26%, 98.23%, 97.06%, and 94.55%, respectively, across fifty epochs. The experimental results validate that the models we have proposed achieve high detection accuracy rates, with the best model reaching up to 99.26% effectiveness, outperforming other models in the diagnosis of pneumonia from X-ray images.
